YAML Metadata Warning: empty or missing yaml metadata in repo card
Check out the documentation for more information.
Moon Crater Navigation - Complete Project
This repository contains the complete Moon Crater Navigation system with crater detection and path planning for lunar surface exploration.
π Project Overview
An AI-powered system for detecting craters on the lunar surface and planning safe navigation paths for autonomous rovers.
Key Features
- π YOLOv8 Crater Detection: State-of-the-art deep learning for crater identification
- πΊοΈ Path Planning: A* algorithm with terrain-aware cost functions
- π¨ Interactive Visualization: 3D terrain visualization and path animation
- π₯οΈ GUI Application: User-friendly interface for mission planning
- π Complete Pipeline: From data processing to deployment
π Project Structure
moon-crater-navigation/
βββ src/ # Source code
β βββ data_processing/ # Data preprocessing and augmentation
β βββ models/ # YOLO training and inference
β βββ navigation/ # Pathfinding algorithms
β βββ visualization/ # Plotting and animation
β βββ utils/ # Helper functions
βββ scripts/ # Standalone scripts
β βββ train_model.py # Model training script
β βββ run_inference.py # Run inference on images
β βββ generate_navigation_path.py
βββ notebooks/ # Jupyter notebooks
β βββ 01_data_preparation.ipynb
β βββ 02_model_training.ipynb
β βββ 03_inference_visualization.ipynb
β βββ 04_path_planning.ipynb
βββ tests/ # Unit tests
βββ app.py # Gradio web demo
βββ models/ # Trained model weights
β βββ best.pt # Best YOLOv8 checkpoint
βββ samples/ # Sample images
βββ data/ # Data configurations
βββ config.json
βββ data.yaml
π Quick Start
Installation
# Clone the repository
git clone https://huggingface.co/JayAtriahf-7/moon-crater-navigation-complete
cd moon-crater-navigation-complete
# Install dependencies
pip install -r requirements.txt
Usage
1. Run the GUI Application
python src/main.py
2. Run the Web Demo
python app.py
Then open http://localhost:7860 in your browser.
3. Use in Code
from src.models.inference import run_inference
from src.navigation.pathfinding import AStarPathfinder
from src.terrain import MoonTerrain
# Detect craters
results = run_inference("path/to/lunar_image.jpg", "models/best.pt")
# Plan navigation path
terrain = MoonTerrain(image_path="path/to/terrain.jpg")
pathfinder = AStarPathfinder(terrain)
path = pathfinder.find_path(start=(10, 10), goal=(90, 90))
π Model Details
- Architecture: YOLOv8s
- Training Data: Chandrayaan + Roboflow lunar crater datasets
- Input Size: 416x416
- Performance: See training notebooks for metrics
π οΈ Development
Training Your Own Model
python scripts/train_model.py --epochs 50 --batch-size 16
Running Tests
pytest tests/
π Documentation
- USER_GUIDE.md - Complete user guide
- DEMO_GUIDE.md - Demo instructions
- DEPLOYMENT_GUIDE.md - How to deploy
- START_HERE.md - Getting started guide
π Live Demo
Try the interactive demo: Hugging Face Space
π Citation
If you use this project in your research, please cite:
@software{moon_crater_navigation,
title = {Moon Crater Navigation System},
author = {JayAtriahf-7},
year = {2025},
url = {https://huggingface.co/JayAtriahf-7/moon-crater-navigation-complete}
}
π― Applications
- Autonomous lunar rover navigation
- Landing site selection and safety analysis
- Mission route planning
- Educational demonstrations
- Research in planetary exploration
π€ Contributing
Contributions are welcome! Feel free to:
- Report bugs
- Suggest features
- Submit pull requests
- Share improvements
π License
MIT License - See LICENSE file for details
π Acknowledgments
- Chandrayaan mission for lunar imagery
- Roboflow for crater detection dataset
- Ultralytics for YOLOv8 framework
π Contact
For questions or collaborations, please open an issue on this repository.
Made with β€οΈ for lunar exploration ππ
Complete project repository - Ready to clone and use!